Building forests of local trees
作者：
Highlights：
• A novel approach in the field of classifier ensembles is proposed.
• The approach uses an ensemble of random decision trees.
• Each decision tree is trained on a different area of the input space.
• Areas can overlap and a good coverage of the input space is ensured.
• Experimental results confirm the validity of the approach.
摘要
•A novel approach in the field of classifier ensembles is proposed.•The approach uses an ensemble of random decision trees.•Each decision tree is trained on a different area of the input space.•Areas can overlap and a good coverage of the input space is ensured.•Experimental results confirm the validity of the approach.
论文关键词：Classifier ensembles,Random forests,Mixture of experts
论文评审过程：Received 19 January 2017, Revised 27 October 2017, Accepted 16 November 2017, Available online 20 November 2017, Version of Record 25 November 2017.
论文官网地址：https://doi.org/10.1016/j.patcog.2017.11.017
